{"id":"https://openalex.org/W4394744760","doi":"https://doi.org/10.1109/tcsvt.2024.3387933","title":"YOWOv3: A Lightweight Spatio-Temporal Joint Network for Video Action Detection","display_name":"YOWOv3: A Lightweight Spatio-Temporal Joint Network for Video Action Detection","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394744760","doi":"https://doi.org/10.1109/tcsvt.2024.3387933"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3387933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3387933","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076304998","display_name":"A. N. Zhu","orcid":"https://orcid.org/0000-0001-8284-727X"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anlei Zhu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114804048","display_name":"Yinghui Wang","orcid":"https://orcid.org/0009-0004-8157-7326"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghui Wang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007738986","display_name":"Jinlong Yang","orcid":"https://orcid.org/0000-0001-9548-4236"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Yang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089927144","display_name":"Tao Yan","orcid":"https://orcid.org/0000-0002-9162-8551"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yan","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010505991","display_name":"Haomiao Ma","orcid":"https://orcid.org/0000-0002-9559-2998"},"institutions":[{"id":"https://openalex.org/I88830068","display_name":"Shaanxi Normal University","ror":"https://ror.org/0170z8493","country_code":"CN","type":"education","lineage":["https://openalex.org/I88830068"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haomiao Ma","raw_affiliation_strings":["School of Computer Science, Shaanxi Normal University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shaanxi Normal University, Xi’an, China","institution_ids":["https://openalex.org/I88830068"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100318161","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-3135-0447"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076304998"],"corresponding_institution_ids":["https://openalex.org/I111599522"],"apc_list":null,"apc_paid":null,"fwci":3.2407,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9301458,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"34","issue":"9","first_page":"8148","last_page":"8160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7353169322013855},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6062496304512024},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5626562237739563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5430724620819092},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4554750919342041},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.44889500737190247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31290531158447266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353169322013855},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6062496304512024},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5626562237739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430724620819092},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4554750919342041},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.44889500737190247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31290531158447266},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3387933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3387933","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G260156416","display_name":null,"funder_award_id":"62172190","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5037605438","display_name":null,"funder_award_id":"2023YFC3805901","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1861492603","https://openalex.org/W1923332106","https://openalex.org/W2102605133","https://openalex.org/W2126579184","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2508429489","https://openalex.org/W2519080876","https://openalex.org/W2611596598","https://openalex.org/W2751445731","https://openalex.org/W2905099632","https://openalex.org/W2905765182","https://openalex.org/W2913950831","https://openalex.org/W2949343965","https://openalex.org/W2951143549","https://openalex.org/W2962790054","https://openalex.org/W2963524571","https://openalex.org/W2963563276","https://openalex.org/W2981548405","https://openalex.org/W2985134635","https://openalex.org/W2985693775","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3096824106","https://openalex.org/W3106250896","https://openalex.org/W3110027162","https://openalex.org/W3165745140","https://openalex.org/W3184439416","https://openalex.org/W3190693140","https://openalex.org/W3195932542","https://openalex.org/W3201233545","https://openalex.org/W3204116406","https://openalex.org/W4226224676","https://openalex.org/W4288277460","https://openalex.org/W4293584584","https://openalex.org/W4297697565","https://openalex.org/W4312509322","https://openalex.org/W4312560592","https://openalex.org/W4312695182","https://openalex.org/W4321012180","https://openalex.org/W4375868868","https://openalex.org/W4377000601","https://openalex.org/W4384284283","https://openalex.org/W4386076325","https://openalex.org/W4386172462","https://openalex.org/W4386541385","https://openalex.org/W6750227808","https://openalex.org/W6751741970","https://openalex.org/W6766773940","https://openalex.org/W6766844300","https://openalex.org/W6779082094","https://openalex.org/W6790307280","https://openalex.org/W6798838024","https://openalex.org/W6849456419"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W2367747139","https://openalex.org/W4391102217","https://openalex.org/W2566187525","https://openalex.org/W2566334511","https://openalex.org/W2367150592","https://openalex.org/W2378889330","https://openalex.org/W4243585476"],"abstract_inverted_index":{"Spatio-temporal":[0],"action":[1,41,109,192],"detection":[2,42,110,193],"networks,":[3],"which":[4,162],"need":[5],"to":[6,24,54,87,123,158,209],"simultaneously":[7],"extract":[8,56,159],"and":[9,12,22,28,38,50,58,75,149,213,246],"fuse":[10],"spatial":[11,57],"temporal":[13,160,211,217],"features,":[14],"often":[15,154],"result":[16],"in":[17,26,112,250,253],"existing":[18,152],"models":[19,111,153],"becoming":[20],"bloated":[21],"difficult":[23],"run":[25],"real-time":[27,39],"deploy":[29],"on":[30,132,166],"edge":[31,188],"devices.":[32],"This":[33,45,205,225,248],"paper":[34],"introduces":[35],"an":[36],"efficient":[37,48,107],"spatio-temporal":[40,66,83,108,191,198,221],"model,":[43],"YOWOv3.":[44],"model":[46,118,208,230],"uses":[47],"3D":[49,156,181,235],"2D":[51,203,258],"backbone":[52],"networks":[53,255],"separately":[55],"spatial-temporal":[59],"features":[60,218],"from":[61,231],"sequential":[62],"information.":[63],"A":[64],"lightweight":[65,254],"feature":[67,222],"fusion":[68],"module,":[69],"designed":[70],"by":[71,120,136],"deeply":[72],"integrating":[73],"convolution":[74,182,236],"self-attention":[76],"mechanisms,":[77],"further":[78],"enhances":[79,240],"the":[80,91,105,117,124,129,133,177,207,215,229,232,241],"extraction":[81,223],"of":[82,114,180,190,234],"features.":[84],"We":[85],"refer":[86],"this":[88],"module":[89,200],"as":[90,170],"CFACM":[92],"(Channel":[93],"Fusion":[94],"&":[95],"Attention":[96],"Convolution":[97],"Mix)":[98],"module.":[99],"Our":[100],"approach":[101],"not":[102,184,226],"only":[103,202,227,257],"outperforms":[104],"latest":[106],"terms":[113],"lightness,":[115],"reducing":[116],"size":[119],"24%":[121],"compared":[122],"latter,":[125],"but":[126,238],"also":[127,239],"improves":[128],"mAP":[130],"accuracy":[131,148,245],"UCF101-24":[134],"dataset":[135],"1.35%,":[137],"while":[138],"maintaining":[139],"excellent":[140],"speed":[141],"performance,":[142],"thus":[143],"achieving":[144],"a":[145,197],"balance":[146,243],"between":[147,244],"speed.":[150,247],"Furthermore,":[151],"use":[155],"convolutions":[157],"information,":[161],"may":[163],"be":[164],"limited":[165],"certain":[167],"devices,":[168],"such":[169],"Apple\u2019s":[171],"M":[172],"series":[173],"processors.":[174],"To":[175],"mitigate":[176],"potential":[178],"issue":[179],"operators":[183],"being":[185],"supported":[186],"during":[187],"deployment":[189],"models,":[194],"we":[195],"employ":[196],"shift":[199],"containing":[201],"convolutions.":[204,259],"enables":[206],"acquire":[210],"information":[212],"inject":[214],"obtained":[216],"into":[219],"multi-level":[220],"models.":[224],"liberates":[228],"constraints":[233],"operations":[237],"model\u2019s":[242],"results":[249],"state-of-the-art":[251],"performance":[252],"using":[256]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}